AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

PatternBloom: Empowering Agentic RAG with Externalized RL-Distilled Graph Patterns

Yi Ge, Heng Huang

NeurIPS 2026 · Large language models › Retrieval and knowledge · approach: Retrieval-augmented reasoning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes PatternBloom, which externalizes reasoning routes over retrieved graph content as reusable patterns distilled via RL for agentic RAG.

Problem

RL-trained agentic RAG systems conflate declarative knowledge (retrieved content) with procedural knowledge (reasoning routes recurring across queries), since the reasoning route stays inside the LLM's hidden state.

Approach

Externalizes the reasoning route through retrieved graph content as graph patterns distilled from RL-trained agents, separating procedural from declarative knowledge; the abstract only partially describes the method.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add PAR pattern-coverage reward (Stage II) (ablation)PatternBloom 7B · HotpotQA/2Wiki/MuSiQue/Bamboogle avgAvg-F1: 44.1 -> 55.9Improved
add Graph Pattern Memory (ablation)PatternBloom 7B · 4 multi-hop avgAvg-F1: 46.6 -> 55.9Improved
add IDR Stage I pre-training (ablation)PatternBloom 7B · 4 multi-hop avgAvg-F1: 52.9 -> 55.9Improved
set shaping weight lambda_p to 0.2 rather than 0.1 (ablation)PAR · 4 multi-hop avgAvg-F1: 45.2 -> 55.9Improved
set shaping weight lambda_p to 0.2 rather than 0.5 (ablation)PAR · 4 multi-hop avgAvg-F1: 43.3 -> 55.9Improved
use full 27-pattern pool instead of top-1 (ablation)GPM retrieval · 4 multi-hop avgAvg-F1: 43.0 -> 55.9Improved
add Stage I (IDR) vs Stage II removal on Bamboogle (ablation)PatternBloom 7B · BamboogleF1: 61.2 vs 66.0 (no PAR), 68.8 (no GPM)Mixed
use PatternBloom instead of Search-R1 7Bagentic RAG 7B · Avg-OODEM: 38.1 -> 49.0Improved
use PatternBloom instead of Structure-R1 on 2Wikiagentic RAG 7B · 2WikiMultiHopQAEM: 69.2 -> 54.0Hurt
add pattern memory to reduce turns vs Graph-R1agentic RAG · Bridge questionsavg turns: 5.4 -> 4.7Improved
scale PatternBloom backbone 7B to 32BPatternBloom · Avg-OODEM: 49.0 -> 52.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy